CS 283 Deep Generative Modeling

This course focuses on generative modeling. The topics covered in this course include Deep Generative Models (VAEs, GANs), Normalizing Flows, infinitesimal flows (Neural ODEs/SDEs, Deep Equilibrium Models), Energy-based Models, Variations and Combinations of Basic Generative Models, Generative Imitation Learning, Genetic Algorithms, Deep Fakes, Aesthetic guided Reinforcement Learning, Style Transfer, Cycle Consistent Generative Models, Creative Adversarial Networks, Algorithmic Art models, and 3D generative models. Story Generation, Transformer-based Text Generation, GPT based Text Generation, and Transformer GANs. All topics are around generative modeling from computer vision, Music, and NLP domains.




Calculus, linear algebra, and preliminary deep learning hands-on background are required (e.g., PyTorch, TensorFlow, or Keras. These can be gained by any course that covers deep learning, even if partially (suggest at least 25% of the course). At KAUST, these courses may include any of these CS220, CS229, C323, CS326, CS320, CS340, or similar experience. The lecturer may also waive the prerequisite for students that demonstrate adequate knowledge of preliminary deep learning practice.